biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[1/N][Attention] Restructure attention: move files (#31916)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-09 16:10:24 -05:00
committed by GitHub
parent 1f8b7c536b
commit 2612ba9285
195 changed files with 426 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/kernels/attention/test_aiter_flash_attn.py
View File

@@ -6,9 +6,9 @@ import pytest
import torch
import vllm.v1.attention.backends.rocm_aiter_fa # noqa: F401
from vllm.attention.utils.fa_utils import is_flash_attn_varlen_func_available
from vllm.platforms import current_platform
from vllm.utils.torch_utils import set_random_seed
from vllm.v1.attention.backends.fa_utils import is_flash_attn_varlen_func_available
NUM_HEADS = [(4, 4), (8, 2)]
HEAD_SIZES = [128, 256]